bestmodel.run / model — Qwen3.8-27B-GGUF (agent view)

category chat · AtomicChat/Qwen3.8-27B-GGUF · 3 runs in the model record
answer: 46.1 tok/s (model median)

Honesty ladder: measured > reported > extrapolated > formula > no data yet.
Empty fields stay empty — never filled with an estimate.

  rig | quant | median result | basis | ttft | peak vram | max context
  RTX 5070 12GB                      | 2-bit | 46 tok/s       | reported | ttft 544ms | vram 10.1 GB | ctx 2,048
  RTX 5090 32GB                      | 6-bit | 98.7 tok/s     | reported | ttft 279ms | vram 29.4 GB | ctx 131,000